Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to specific pages or sections within a document

    oai_token-act-pair · gpt-3.5-turbo

    references to specific games, rounds, and other numerical identifiers related to sports or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ersen
    -0.74
     Gazette
    -0.71
    ccording
    -0.70
    glomer
    -0.67
    ricks
    -0.66
    uctor
    -0.65
     congratulated
    -0.65
     grate
    -0.64
    apest
    -0.63
    yssey
    -0.62
    POSITIVE LOGITS
     orders
    0.67
     mode
    0.66
     proportions
    0.65
     communism
    0.64
     quarters
    0.63
    runs
    0.63
    Cre
    0.62
     bounds
    0.61
     margins
    0.61
    ãģĨ
    0.61
    Act Density 0.318%

    No Known Activations